Week 4, 2026 Season, Top 10 SRS

By SRS, the best team in football is Jacksonville, followed by San Francisco and Chicago. Conspicuous in its absence is Seattle, which dominated late last year. Another last year favorite, LA, is merely at 10th place.

NAME   W  L  T    SRS   OSRS   DSRS    MOV    SOS
--------------------------------------------------
JAX    3  1  0  15.59   2.89  12.70  12.75   2.84
SF     4  0  0  14.32   7.21   7.11  14.50  -0.18
CHI    3  1  0  12.31   4.89   7.42  11.75   0.56
KC     4  0  0  12.00   6.87   5.13  10.25   1.75
MIN    4  0  0   7.65  -2.70  10.36   8.75  -1.10
DEN    2  2  0   6.32  -4.11  10.43  -5.00  11.32
LV     3  1  0   6.13   5.64   0.49   7.75  -1.62
CAR    2  2  0   4.90   9.05  -4.14   3.00   1.90
CIN    2  2  0   3.86   1.14   2.72   3.00   0.86
LA     2  2  0   3.37  -1.86   5.23   0.50   2.87

 

Week 4, 2026 Season

On week 4, there have been enough games played to resolve SRS for all teams in the NFL. Without further ado, the results are given below. Of the 4-0 teams Minnesota has to be the most surprising. Jacksonville is the best 3-1 team and has the best SRS overall, and the Denver Broncos are the best of the 2-2 teams.

Global Statistics:
Games  Home Wins HwPct Winning_Score Losing_Score Margin
64         36     56.2      28.25        17.97     10.28

Calculated Pythagorean Exponent:  3.69


Rank  Team    Median  GP   W   L   T  Pct   Pred   SRS    MOV   SOS
------------------------------------------------------------------------
1     SF      15.0     4   4   0   0 100.0  91.6  14.32  14.50 -0.18
2     KC       8.5     4   4   0   0 100.0  82.9  12.00  10.25  1.75
3     MIN      6.5     4   4   0   0 100.0  87.3   7.66   8.75 -1.09
4     CHI     15.5     4   3   1   0  75.0  88.2  12.31  11.75  0.56
5     JAX     14.5     4   3   1   0  75.0  92.3  15.59  12.75  2.84
6     LV      10.0     4   3   1   0  75.0  76.1   6.13   7.75 -1.62
7     BUF      6.5     4   3   1   0  75.0  65.3   0.59   5.00 -4.41
8     NYG      6.5     4   3   1   0  75.0  53.4  -3.32   0.75 -4.07
9     SEA      5.0     4   3   1   0  75.0  79.3   1.59   8.00 -6.41
10    BAL      4.5     4   3   1   0  75.0  66.8  -0.02   5.00 -5.02
11    CLE      3.0     4   3   1   0  75.0  35.7   0.14  -3.50  3.64
12    ATL      7.0     4   2   2   0  50.0  53.9  -1.73   1.00 -2.73
13    CAR      1.5     4   2   2   0  50.0  59.5   4.90   3.00  1.90
14    CIN      1.5     4   2   2   0  50.0  62.0   3.86   3.00  0.86
15    DAL      0.5     4   2   2   0  50.0  57.8  -2.54   2.50 -5.04
16    LA       0.0     4   2   2   0  50.0  52.2   3.37   0.50  2.87
17    PIT      0.0     4   2   2   0  50.0  38.9  -1.68  -2.50  0.82
18    NE       0.0     4   2   2   0  50.0  34.8   1.02  -3.00  4.02
19    IND     -0.5     4   2   2   0  50.0  48.2  -1.71  -0.50 -1.21
20    PHI     -1.0     4   2   2   0  50.0  31.1  -5.84  -4.50 -1.34
21    DET     -2.5     4   2   2   0  50.0  44.0  -3.10  -2.00 -1.10
22    DEN     -3.0     4   2   2   0  50.0  29.2   6.32  -5.00 11.32
23    GB      -7.0     4   2   2   0  50.0  20.7  -8.70  -8.00 -0.70
24    NO      -4.5     4   1   3   0  25.0  32.5  -5.43  -5.75  0.32
25    NYJ     -5.0     4   1   3   0  25.0  40.9  -4.48  -2.00 -2.48
26    ARI     -9.0     4   1   3   0  25.0  25.1  -6.69  -7.50  0.81
27    WAS     -9.5     4   1   3   0  25.0  23.0 -10.62  -8.50 -2.12
28    HOU     -4.5     4   0   4   0   0.0  27.6  -6.20  -6.25  0.05
29    TB      -5.0     4   0   4   0   0.0  29.7  -4.26  -5.00  0.74
30    TEN     -5.5     4   0   4   0   0.0  17.9 -10.41  -7.00 -3.41
31    LAC    -10.0     4   0   4   0   0.0  15.5  -9.34  -9.75  0.41
32    MIA    -14.0     4   0   4   0   0.0   5.2  -3.72 -13.75 10.03

 

2026 and a new data feed

Week 3 of the NFL season has ended and it’s around week 3 or 4 that SRS resolves, so I started trying to download data into my database. Oh, guess what, my old scraper is blocked. So, the fix is nflfastR.com, as it has data, dating back many years, and in that data are EPA based results. The kinds of things you can analyze from that data set are well documented on Twitter by @benbaldwin, so look at some of his tweets to see all its uses. Next, I spent maybe 15 minutes asking AI how I could get these data, and to a large extent, it wrote the Perl I need to get the data I want. Of course, the code broke, and I spent some time fixing it.

Below is the fixed code that AI gave me. It’s hacky, but shows that nflfastR can be accessed by a variety of tools, not just R.

#! /usr/bin/perl
use strict;
use warnings;
use WWW::Mechanize;
use Text::CSV;
use IO::Uncompress::Gunzip qw(gunzip $GunzipError);
use Data::Dumper;
# Define target year/season
my $target_year = 2026;
# Primary nflverse URL for schedules and scores
my $url = 'https://github.com';
my $url = 'https://github.com/nflverse/nflverse-data/releases/download/pbp/play_by_play_' . $target_year . '.csv.gz';
print $url,"\n";
# 1. Initialize Mechanize and fetch the file
my $mech = WWW::Mechanize->new( autocheck => 1 );
print "Fetching game score data from nflverse...\n";
$mech->get($url);
# Extract raw downloaded content
my $raw_content = $mech->content;
# 2. Decompression handling
# If the server returned gzip or the file signature suggests gzip, decompress it.
my $decompressed_content;
if ( $raw_content =~ /^\x1f\x8b/ ) { # Gzip magic number check
    print "Decompressing gzipped data layer...\n";
    gunzip \$raw_content => \$decompressed_content
        or die "Decompression failed: $GunzipError\n";
} else {
    $decompressed_content = $raw_content;
}
# print $decompressed_content;
# exit 7;
my $csv = Text::CSV->new({ 
    binary   => 1, 
    auto_diag => 1,
    #    headers  => 'auto' # Automatically treats the first line as columns
});
open my $fh, '<', \$decompressed_content or die "Failed to open memory buffer: $!";
$csv->header($fh);
my @games_array;
print "Filtering game scores for the $target_year season...\n";
# 4. Parse line-by-line and load into array
while ( my $row = $csv->getline_hr($fh) ) {
    # Skip rows that don't match our target season year
    next unless $row->{season} == $target_year;
    
    # Construct individual game object pushing required fields
    push @games_array, {
        game_id    => $row->{game_id},
        season     => $row->{season},
        week       => $row->{week},       # The requested week field
        home_team  => $row->{home_team},
        away_team  => $row->{away_team},
        home_score => $row->{home_score},
        away_score => $row->{away_score},
        game_type  => $row->{game_type},  # REG or POST season
    };
}
close $fh;
print "Successfully loaded " . scalar(@games_array) . " games into the array.\n\n";
print "Sample Data (First 2 entries):\n";
print Dumper( [ @games_array[0..1] ] );

Totally unrelated to all this, but as I have retired, I am writing a novel here: https://www.royalroad.com/fiction/184090/reborn-as-an-orc

 

2025 Super Bowl Worksheet. Formula + SRS.

The two Super Bowl teams are now set. Both games were close and every team in this round could have won. But it’s Seattle and New England in the final game of the season and they made it there the old fashioned way, by earning it. I am presenting both Formula and SRS formulas, and to date, SRS has been far more reliable at predicting the New England games, as the formula dislikes New England.

Super Bowl Odds
Home Team	Visiting Team	Score Diff	Win Prob	Est. Point Spread
Seattle Seahawks	NE Patriots	2.477	0.92	18

The more reliable method of predicting New England games has been Simple Ranking, so we present those results below.

Super Bowl Odds SRS Based
Home Team	Visiting Team	Score Diff	Win Prob	Est. Point Spread
Seattle Seahawks	NE Patriots	0.936	0.72	6.9

In both cases Seattle is favored, though the more realistic odds scenario gives the Seahawks almost a 7 point advantage. My genuine hope is the game is exciting. These two teams have the muscle to make it so.

 

2025 Conference Championship Worksheet, Formula + SRS

We are now down to four teams. New England made it here as C J Stroud gave up too many turnovers. Denver-Bills and Bears-Rams were close games. Seattle won in a blowout. Looking for data on the effects of losing a QB starter, AI suggested it affects an offense by 4 EP. Just note that EP is not the same thing as points, as you generate lots of EP by running up and down the field. Anyway, on to formulas.

Conference (NFC/AFC) Playoff Odds
Home Team	Visiting Team	Score Diff	Win Prob	Est. Point Spread
Seattle Seahawks	LA Rams	0.423	0.60	3.1
Denver Broncos	New England Patriots	1.562	0.83	11.6

I would not bet my formula on any game involving new England, as NE is not the kind of team my model likes, but New England is winning anyway. If you want a better representation of New England’s prowess, use the SRS formulas below. SRS based formulas have an added 3.8 point home field advantage.

Conference (NFC/AFC) Playoff Odds SRS based
Home Team	Visiting Team	Score Diff	Win Prob	Est. Point Spread
Seattle Seahawks	LA Rams	0.571	0.64	4.1
Denver Broncos	New England Patriots	0.161	0.54	1.2

I will note that model or formula, these calculations favor the home teams. Now, if Bo Nix was worth, say, 3 points, then New England would be favored by 1.8 points by adjusted SRS.

 

2025 Second round Worksheet. Formula + SRS

While Seattle, our #1 favorite, did not play, our AFC pick, Jacksonville, succumbed to a set of turnovers and lost a tough game to the Buffalo Bills. The formula was not as successful as raw SRS this year, perhaps because teams like New England don’t fit our model. That said, these are the formula predictions for the second round of the playoffs.

2025 Second Round Playoff Odds
Home Team	Visiting Team	Score Diff	Win Prob	Est. Point Spread
Seattle Seahawks	SF 49ers	0.423	0.604	3.1
Chicago Bears	LA Rams	-1.048	0.260	-7.7
Denver Broncos	Buffalo Bills	0.809	0.692	6.0
New England Patriots	Houston Texans	-2.105	0.109	-15.6

The formula doesn’t like New England and doesn’t like Chicago either, so predicts losses for both. The results of a traditional offensive metric such as SRS are somewhat different. The SRS results include a 3.8 point home field advantage.

2025 Second Round Playoff Odds SRS based.
Home Team	Visiting Team	Score Diff	Win Prob	Est. Point Spread
Seattle Seahawks	SF 49ers	1.442	0.809	10.7
Chicago Bears	LA Rams	-1.115	0.247	-8.3
Denver Broncos	Buffalo Bills	0.374	0.592	2.8
New England Patriots	Houston Texans	0.099	0.525	0.7

The SRS results still don’t favor the Bears, but New England is slightly favored and Denver – Bills comes out as a close game.

 

2025 Playoff Season Worksheet. First Round Odds. Formula plus SRS

The formula for calculating these odds are given here.

The teams most favored by the playoff formula are the Seattle Seahawks and the Jacksonville Jaguars. Seattle is favored throughout the NFC playoffs. Jacksonville, as a #3 seed, will lose the HFA after its first round game, unless the #2 team, New England, loses. The teams least favored by the playoff model are New England, Buffalo, and Chicago. For comparison we have also calculated SRS based odds for all the playoff games, adding a 3.8 point HFA to the home team.

(PX within 2 years) Logit P = 0.660 + 0.304(SOS) + 0.747(PPX)

2025 NFL Playoff Teams, C&F Worksheet.
NFC
Rank	Name	Home Field Adv	Playoff Experience	SOS	Total Score
1	Seattle Seahawks	0.660	0.747	0.429	1.836
2	Chicago Bears	0.660	0.0	-0.386	0.274
3	Philadelphia Eagles	0.660	0.747	-0.249	1.158
4	Carolina Panthers	0.660	0.0	0.088	0.748
5	LA Rams	0.0	0.747	0.666	1.413
6	SF 49ers	0.0	0.747	0.575	1.322
7	Green Bay Packers	0.0	0.747	-0.316	0.431
AFC
1	Denver Broncos	0.660	0.747	-0.486	0.921
2	NE Patriots	0.660	0.0	-1.301	-0.641
3	Jacksonville Jaguars	0.660	0.747	0.249	1.656
4	Pittsburgh Steelers	0.660	0.747	0.097	1.504
5	Houston Texans	0.0	0.747	0.717	1.464
6	Buffalo Bills	0.0	0.747	-0.635	0.112
7	LA Chargers	0.0	0.747	-0.192	0.555

Using the data above, we can calculate playoff odds for the first round. As this is a simple static model, it will not yield the same odds as a model based on offensive stats.

First Round Playoff Odds
Home Team	Visiting Team	Score Diff	Win Prob	Est. Point Spread
Chicago Bears	Green Bay Packers	-0.157	0.461	-1.2
Philadelphia Eagles	SF 49ers	-0.164	0.459	-1.2
Carolina Panthers	LA Rams	-0.665	0.339	-4.9
NE Patriots	LA Chargers	-1.196	0.232	-8.9
Jacksonville Jaguars	Buffalo Bills	1.544	0.824	11.4
Pittsburgh Steelers	Houston Texans	0.040	0.510	0.3

The following odds are calculated with Simple Rankings. These will more closely follow formulas using DVOA, ESPN, Vegas based odds or other scoring stats.

First Round Playoff Odds SRS based
Home Team	Visiting Team	Score Diff	Win Prob	Est. Point Spread
Chicago Bears	Green Bay Packers	0.446	0.610	3.3
Philadelphia Eagles	SF 49ers	0.338	0.583	2.5
Carolina Panthers	LA Rams	-1.65	0.161	-12.2
NE Patriots	LA Chargers	1.148	0.759	8.5
Jacksonville Jaguars	Buffalo Bills	1.081	0.747	8.0
Pittsburgh Steelers	Houston Texans	-0.419	0.397	-4.9

In both systems, Jacksonville-Buffalo is considered an easy win for Jax. The Pittsburgh-Texans came is close by the playoff model but an easy enough win for the Texans using SRS. Chicago – Green Bay and Philadelphia – 49ers are close in either system, with the playoff model favoring visitors and SRS favoring the home teams. Carolina – Rams is a hard loss for the home team via either system.

 

Week 18, 2025 Season, Top 10 SRS

Jacksonville moves up from fourth place to third, and Philadelphia is just outside the top 10 in 11th place. Seattle ends the season as #1 with the Rams close behind. The injury to Daniel Jones leaves Indianapolis as the biggest ‘what if’ of the year.

NAME   W  L  T    SRS   OSRS   DSRS    MOV    SOS
--------------------------------------------------
SEA   14  3  0  12.64   6.39   6.33  11.24   1.41
LA    12  5  0  12.31   8.63   3.75  10.12   2.19
JAX   13  4  0   8.94   5.02   3.82   8.12   0.82
HOU   12  5  0   8.78   1.70   7.18   6.41   2.36
SF    12  5  0   5.77   3.83   1.89   3.88   1.89
NE    14  3  0   5.71   3.42   2.19  10.00  -4.29
IND    8  9  0   5.16   4.55   0.52   3.18   1.99
BUF   12  5  0   4.73   3.89   0.79   6.82  -2.09
DEN   14  3  0   3.70  -1.00   4.57   5.29  -1.60
DET    9  8  0   3.67   5.43  -1.79   4.00  -0.33

 

Week 18, 2025 Season

Sorry about the delay, flu had me in its grip this week. With the final week of the season, the last playoff teams have been decided and we have the data necessary for calculating playoff odds.

Global Statistics:
Games  Home Wins HwPct Winning_Score Losing_Score Margin
272       146     53.7      28.44        17.29     11.15

Calculated Pythagorean Exponent:  3.04


Rank  Team    Median  GP   W   L   T  Pct   Pred   SRS    MOV   SOS
------------------------------------------------------------------------
1     SEA      8.0    17  14   3   0  82.4  82.2  12.64  11.24  1.41
2     NE       6.0    17  14   3   0  82.4  78.5   5.72  10.00 -4.28
3     DEN      3.0    17  14   3   0  82.4  68.4   3.70   5.29 -1.60
4     JAX      6.0    17  13   4   0  76.5  74.0   8.94   8.12  0.82
5     LA       7.0    17  12   5   0  70.6  77.4  12.31  10.12  2.19
6     BUF      5.0    17  12   5   0  70.6  69.9   4.73   6.82 -2.09
7     SF       4.0    17  12   5   0  70.6  62.2   5.77   3.88  1.89
8     HOU      4.0    17  12   5   0  70.6  72.3   8.78   6.41  2.36
9     PHI      3.0    17  11   6   0  64.7  61.5   2.56   3.18 -0.62
10    LAC      3.0    17  11   6   0  64.7  56.0   1.02   1.65 -0.63
11    CHI      2.0    17  11   6   0  64.7  54.6   0.26   1.53 -1.27
12    PIT      2.0    17  10   7   0  58.8  51.9   0.27   0.59 -0.32
13    GB       4.0    17   9   7   1  55.9  56.3   0.78   1.82 -1.04
14    DET      3.0    17   9   8   0  52.9  61.4   3.67   4.00 -0.33
15    MIN      3.0    17   9   8   0  52.9  52.5   0.54   0.65 -0.11
16    BAL     -1.0    17   8   9   0  47.1  54.8   1.34   1.53 -0.19
17    TB      -1.0    17   8   9   0  47.1  44.1  -1.26  -1.82  0.56
18    ATL     -1.0    17   8   9   0  47.1  40.4  -2.96  -2.82 -0.13
19    IND     -2.0    17   8   9   0  47.1  59.3   5.16   3.18  1.99
20    CAR     -2.0    17   8   9   0  47.1  35.2  -3.77  -4.06  0.29
21    DAL     -3.0    17   7   9   1  44.1  43.8  -4.31  -2.35 -1.96
22    MIA     -3.0    17   7  10   0  41.2  35.2  -6.12  -4.53 -1.59
23    KC      -3.0    17   6  11   0  35.3  57.5   2.13   2.00  0.13
24    CIN     -5.0    17   6  11   0  35.3  37.2  -4.93  -4.59 -0.34
25    NO      -5.0    17   6  11   0  35.3  33.6  -5.07  -4.53 -0.54
26    CLE     -4.0    17   5  12   0  29.4  28.2  -7.16  -5.88 -1.28
27    WAS     -7.0    17   5  12   0  29.4  32.7  -5.93  -5.59 -0.34
28    NYG     -7.0    17   4  13   0  23.5  39.4  -3.83  -3.41 -0.42
29    ARI     -4.0    17   3  14   0  17.6  27.5  -4.59  -7.82  3.24
30    TEN    -10.0    17   3  14   0  17.6  17.0  -7.77 -11.41  3.64
31    LV     -11.0    17   3  14   0  17.6  14.5 -10.29 -11.24  0.95
32    NYJ    -13.0    17   3  14   0  17.6  17.2 -12.33 -11.94 -0.39

 

Week 17, 2025 Season, Top 10 SRS

The Falcons upset has led to a change at the top, with both LA and Seattle having the same SRS to four significant digits, but Seattle having a little more. San Francisco is surging up the ranks. Jacksonville is solidly in fourth. Denver remains just outside the top 10, at an SRS of 2.99.

NAME   W  L  T    SRS   OSRS   DSRS    MOV    SOS
--------------------------------------------------
SEA   13  3  0  12.36   6.69   5.88  11.31   1.05
LA    11  5  0  12.36   8.09   4.27   9.69   2.68
HOU   11  5  0   8.50   0.21   8.03   6.31   2.19
JAX   12  4  0   7.97   3.99   3.95   6.50   1.47
SF    12  4  0   5.88   4.53   1.69   4.75   1.13
IND    8  8  0   5.46   4.18   1.55   3.88   1.59
NE    13  3  0   4.71   2.70   2.00   8.88  -4.17
BUF   11  5  0   4.23   3.34   0.76   5.56  -1.33
DET    8  8  0   3.75   5.81  -2.16   4.06  -0.32
PHI   11  5  0   3.44  -0.44   4.09   3.81  -0.37